pvary commented on a change in pull request #2173: URL: https://github.com/apache/hive/pull/2173#discussion_r612999086
########## File path: iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/HiveTableUtil.java ########## @@ -0,0 +1,142 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +package org.apache.iceberg.mr.hive; + +import java.io.IOException; +import java.net.URI; +import java.net.URISyntaxException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.List; +import java.util.Map; +import java.util.concurrent.Callable; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.Executors; +import java.util.concurrent.Future; +import java.util.stream.Collectors; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.FileSystem; +import org.apache.hadoop.fs.Path; +import org.apache.hadoop.fs.PathFilter; +import org.apache.hadoop.hive.conf.HiveConf; +import org.apache.hadoop.hive.metastore.Warehouse; +import org.apache.hadoop.hive.metastore.api.Partition; +import org.apache.hadoop.hive.metastore.partition.spec.PartitionSpecProxy; +import org.apache.iceberg.AppendFiles; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.MetricsConfig; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.mapping.NameMapping; +import org.apache.iceberg.mapping.NameMappingParser; +import org.apache.iceberg.relocated.com.google.common.util.concurrent.ThreadFactoryBuilder; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class HiveTableUtil { + + private static final Logger LOG = LoggerFactory.getLogger(HiveTableUtil.class); + + private static class DataFileFilter implements PathFilter { Review comment: I have concerns with this: - AFAIK Hive allows directories under a table, and scans them for files for normal tables. So we might want to handle directories. - `fileSystem.isFile(path)` is an extra call for every file. This could be very-very costly for big tables. Any way to avoid the call? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
